GPT-Live 1 + GPT-6 Sol vs Phonic v1

Phonic v1 is more reliable, by 14.6 points. GPT-Live 1 + GPT-6 Sol passed 62 of 82 scenarios on all three runs, and Phonic v1 passed 74. A scenario only counts when every run of it passed.

For a voice agent, Phonic v1, since it gets more scenarios right on every run. Phonic v1 is ahead on reliability, success rate, data accuracy, calls where the agent went quiet and response time, and GPT-Live 1 + GPT-6 Sol on agent responses, interruption and cost.

Phonic v1, by 8.4 points. GPT-Live 1 + GPT-6 Sol saved everything exactly right on 89.0% of the calls that save data, and Phonic v1 on 97.5%. On Booking calls, 100.0% against 100.0%. On Medicare calls, 60.6% against 90.9%. A call counts only when nothing is missing, wrong, extra or saved twice.

No. Phonic v1 starts replying 0.39s sooner at the median. GPT-Live 1 + GPT-6 Sol takes 2.02s at the median and 2.42s at p90; Phonic v1 takes 1.63s and 1.81s. Both are measured on the call audio, from the caller finishing to the agent starting to reply.

GPT-Live 1 + GPT-6 Sol, by 0.01 on a 0 to 5 scale. GPT-Live 1 + GPT-6 Sol scores 4.89 and Phonic v1 4.88 for how well the agent handled being talked over.

Phonic v1, by 12.2 points. The agent went quiet for 10 seconds or more on 12.2% of GPT-Live 1 + GPT-6 Sol calls and 0.0% of Phonic v1 calls.

GPT-Live 1 + GPT-6 Sol is $0.0047 cheaper a minute. GPT-Live 1 + GPT-6 Sol costs $0.0553 a minute of call and Phonic v1 $0.0600, at each vendor's published rates.

Cekura ran both as the whole agent in the same open-source Pipecat pipeline, with the same prompt, tools and connection. A simulated caller worked through all 82 scenarios on live calls, three times each, 3,690 calls across the benchmark. A call passes only when the agent said the right things and saved the right data.